Constructing an AI Agent with Llama 4 and AutoGen

Meta’s Llama 4 household of fashions is presently ruling the ever-advancing world of AI. These fashions are revolutionizing how we construct clever techniques with their native multimodal capabilities. When Llama 4 combines with AutoGen, it unlocks the total potential of constructing dynamic, responsive, and sturdy AI Brokers. By leveraging the mixing between Llama 4 and AutoGen, builders can create progressive AI brokers that may motive, collaborate, and adapt effectively. On this article, we’ll discover ways to construct AI brokers with Llama 4 and AutoGen for particular functions.

Why Ought to We Contemplate Utilizing Llama 4?

The Llama 4 mannequin household, together with Scout and Maverick variants, represents a big leap ahead in open-source AI know-how. These fashions provide a number of key benefits:

• Multimodal Intelligence: Llama 4 options native multimodal capabilities that combine several types of enter right into a unified structure. This allows extra subtle reasoning throughout totally different media sorts.
• Giant Context Size: It helps as much as 10 million tokens, increasing on Llama 3‘s 128K restrict. It allows dealing with exceptionally lengthy contexts. This makes potential superior functions like complete multi-document evaluation, intensive personalization primarily based on person historical past, and navigation of enormous codebases.
• Environment friendly Efficiency: Llama 4 employs a Combination of Knowledgeable structure that prompts solely particular parts of the mannequin for every token processed. This strategy makes the fashions extremely environment friendly. Llama 4 Maverick, as an example, makes use of simply 17 billion of its whole 400 billion parameters throughout operation. This enables it to run on a single H100 DGX host.
• Superior Efficiency and Capabilities: Benchmark testing reveals Llama 4 Maverick outperforming comparable fashions like GPT-4o and Gemini 2.0 throughout coding, reasoning, multilingual capabilities, and picture understanding.
• Open Supply and Accessible: Meta is making fashions out there for obtain. This encourages open innovation, enabling builders to customise and deploy the know-how throughout various functions and platforms.

Additionally Learn: DeepSeek V3 vs. Llama 4: Selecting the Proper AI Mannequin for You

Llama 4 Benchmark Efficiency

To grasp simply how good this mannequin is, right here’s a comparability of Llama 4 towards different high fashions on numerous normal benchmarks.

 Additionally Learn: Llama 4 vs. GPT-4o: Which is Higher for RAGs?

Constructing an AI Agent Utilizing Llama 4

On this part, I’ll stroll you thru the method of constructing task-specific brokers utilizing Llama 4 and AutoGen. We are going to create a multi-agent system that analyzes shopper necessities for a job, finds freelancers for the actual job primarily based on their expertise and particulars, after which generates customized job proposals for the person to ship out. So let’s start.

Additionally Learn: Palms-on Information to Constructing Multi-Agent Chatbots with AutoGen

Step 0: Setting Up the Surroundings

Earlier than constructing the agent, we’ll first cowl the mandatory stipulations and arrange the atmosphere.

Conditions

Accessing the API

We might be utilizing the Collectively API right here to entry the Llama 4 mannequin. Create an account on Collectively AI and go to this web page to create your secret key: https://api.collectively.xyz/

Step 1: Organising Libraries and Instruments to Information the AI Brokers

First, we might be importing all the mandatory libraries and instruments that we’ll want right here.

import os
import autogen
from IPython.show import show, Markdown

Step 2: Calling the API

To make use of the Llama 4, we now have to load the Collectively API. The code block beneath will assist us load the APIs and configure them to the atmosphere.

with open("together_ai_api.txt") as file:
   LLAMA_API_KEY = file.learn().strip()
os.environ["LLAMA_API_KEY"] = LLAMA_API_KEY

Step 3: Creating Brokers and Defining Duties

Now, let’s create the required brokers and outline their duties, i.e., what they’ll do.

1. Consumer Enter Agent

The Consumer Enter agent acts as the first interface between the human person and the agent system. It collects venture particulars like shopper necessities, timeline, and funds from the person and passes them to the Scope Architect. It additionally relays follow-up questions and solutions, and alerts termination when the ultimate proposal is accepted.

Anticipated Output:

• Clear transmission of the person’s venture description and freelancer profile (expertise, expertise, time estimate).
• Ends the session as soon as a passable proposal is delivered, or the person will explicitly finish it.

# Agent 1: Handles Human Enter for Consumer Necessities
client_agent = autogen.UserProxyAgent(
   identify="Client_Input_Agent",
   human_input_mode="ALWAYS",  # asks the human for enter
   max_consecutive_auto_reply=1, # Solely reply as soon as
   is_termination_msg=lambda x: x.get("content material", "").rstrip().endswith("TERMINATE"),
   system_message="""You're the main level of contact for the person.
   Your first job is to offer the preliminary venture particulars acquired from the human person (shopper necessities, product particulars, timeline, funds) to the group chat.
   After the Scope Architect asks questions, relay the human person's solutions about their expertise, expertise, instruments, and time estimate again to the chat.
   Reply TERMINATE when the ultimate proposal is generated and passable, or if the person needs to cease. In any other case, relay the person's enter.
   """,
)

2. Scope Architect Agent

The Scope Architect Agent is accountable for the preliminary venture particulars from the Consumer Enter Agent. After that, it asks particular questions to assemble the freelancer’s expertise, instruments, previous venture expertise, and estimated time to finish the work. It doesn’t proceed to proposal era itself however ensures that every one the mandatory context is collected earlier than handing it over to the subsequent agent.

Anticipated Output:

• Nicely-structured abstract combining each the shopper’s venture wants and the freelancer’s capabilities.
• Triggers the Fee Recommender Agent as soon as all required knowledge is collected and summarized.

# Agent 2: Gathers Person's Profile and Estimates
scope_architect_agent = autogen.AssistantAgent(
   identify="Scope_Architect",
   llm_config=llm_config,
   human_input_mode="ALWAYS",
   max_consecutive_auto_reply=1, # Solely reply as soon as 
   is_termination_msg=lambda x: x.get("content material", "").rstrip().endswith("TERMINATE"),
   system_message="""You're a Scope Architect. Your position is to grasp the venture necessities supplied initially after which collect essential particulars *from the Client_Input_Agent (representing the person/freelancer)*.
   1. Anticipate the preliminary venture particulars from Client_Input_Agent.
   2. After getting the venture particulars, formulate clear questions for the Client_Input_Agent to ask the human person about their:
       - Related previous work/initiatives and collaborations.
       - Key expertise and instruments relevant to this venture.
       - Their estimated time to finish the outlined work.
   3. Do NOT proceed to proposal era. Anticipate the Client_Input_Agent to offer the person's solutions.
   4. After getting each the shopper necessities AND the person's particulars (expertise, expertise, time estimate), summarize this info clearly for the Fee Recommender. Sign that you've all essential data.
   """,
)

3. Fee Recommender Agent

The Fee Recommender Agent makes use of the collected info to generate an in depth venture proposal. It waits for the entire abstract from the Scope Architect. Then analyzes the venture scope and freelancer particulars to generate knowledgeable proposal doc. This features a customized introduction, a timeline, a number of pricing tiers, and a transparent name to motion.

Anticipated Output:

• Professionally formatted venture proposal doc with a scope, pricing, and subsequent steps.
• The ultimate output is able to be delivered to the shopper for approval or additional dialogue.

rate_recommender_agent = autogen.AssistantAgent(
   identify="Rate_Recommender",
   llm_config=llm_config,
   max_consecutive_auto_reply=1, # Solely reply as soon as
   system_message=f"""
You're a Proposal Generator and Fee Recommender. Your job is to create a structured venture proposal.
Wait till the Scope_Architect shares a abstract containing BOTH the shopper's venture necessities AND the person's profile (expertise, expertise, time estimate, previous work if out there).
Analyze all acquired knowledge: shopper wants, person experience, estimated time, and any prior charge insights.
Generate a well-structured proposal addressed to the shopper, together with the next sections:
Customized Introduction: Professionally introduce the person's providers and reference the shopper's firm and venture.
Undertaking Scope & Timeline: Clearly define the deliverables with estimated timelines primarily based on person enter.
Advised Pricing Tiers: Present 1–3 pricing choices (hourly, fastened charge, retainer) with justifications primarily based on scope, person expertise, or complexity.
Subsequent Steps (CTA): Advocate scheduling a short kickoff name to finalize and make clear particulars.
Current ONLY the ultimate formatted proposal. Don't embrace further commentary except clarification is requested.""",)

4. Person Proxy Agent

This agent acts as an entry level or helper to kick off the interplay. Although it doesn’t play a central position on this stream (primarily based on the code supplied), it might be used to provoke or help with user-facing duties.

user_proxy = autogen.UserProxyAgent(
   identify="user_proxy",
   max_consecutive_auto_reply=1,
   # is_termination_msg=lambda x: x.get("content material", "").rstrip().endswith("TERMINATE"),
   llm_config=llm_config,
   system_message="""you might be an useful assistant and initate the dialog"""
)

Step 4: Creating the Group Supervisor

This step units up the central coordinator that manages communication and teamwork between all specialised brokers.

1. Setting Up Group Chat

The Group Chat establishes a structured dialog atmosphere for 3 specialised brokers. These are the shopper agent, scope architect agent, and charge recommender agent. It manages dialog stream by way of spherical limits and orderly speaker choice.

Key factors:

• Homes three specialised brokers working towards proposal creation
• 4 rounds most to keep up focus
• “Round_robin” talking sample ensures orderly participation
• Creates a managed atmosphere for gathering info

# --- Group Chat Setup ---
groupchat = autogen.GroupChat(
   brokers=[client_agent, scope_architect_agent, rate_recommender_agent],
   messages=[],
   max_round=4,
   speaker_selection_method="round_robin",
)

2. Creating the Group Chat Supervisor

The Group Chat Supervisor orchestrates all the dialog, guiding interactions by way of a logical development from venture particulars to proposal era. Its system message supplies step-by-step directions for agent interactions and defines clear termination situations.

Key factors:

• Directs dialog stream between all brokers
• Hyperlinks to the Group Chat object
• Maintains constant LLM configuration
• Incorporates detailed course of directions
• Terminates upon proposal completion or with the TERMINATE command

supervisor = autogen.GroupChatManager(
   groupchat=groupchat,
   llm_config=llm_config,
   # System message for the supervisor guiding the general stream
   system_message="""Handle the dialog stream between the brokers.
   1. Begin with the Client_Input_Agent offering venture particulars.
   2. Make sure the Scope_Architect asks the mandatory questions concerning the person's background.
   3. Make sure the Client_Input_Agent relays the person's solutions.
   4. Make sure the Rate_Recommender waits for all data earlier than producing the ultimate proposal within the specified format.
   The dialog finishes when the ultimate proposal is generated or the Client_Input_Agent says TERMINATE."""
)

Step 5: Initiating the Chat

Now that we now have the brokers in place, let’s provoke the collaborative workflow between the brokers. For this, we’ll ship a transparent instruction immediate to the GroupChatManager from the user_proxy agent.

Key factors:

• Triggers the dialog through the use of user_proxy.initiate_chat(), which begins the group chat and sends the message to the GroupChatManager.
• Delegates management to the supervisor, which then follows the step-by-step stream utilizing the round-robin methodology and its inside system message directions to coordinate the brokers.

# --- Provoke Chat ---


print("Beginning the proposal era course of...")
print("Please present the preliminary shopper and venture particulars when prompted.")


initial_prompt_message = """
Begin the method. First, I would like the shopper/venture particulars from the person (by way of Client_Input_Agent).
Then, Scope_Architect ought to ask the person (by way of Client_Input_Agent) about their background.
Lastly, Rate_Recommender ought to generate the proposal.
"""


user_proxy.initiate_chat(
   supervisor,
   message=initial_prompt_message
)

Step 6: Formatting the Output

This code will assist us current the output in a markdown(.md) format.

chat_history = supervisor.chat_messages[client_agent] # Or probably simply supervisor.chat_messages if construction differs barely


# Discover the final message from the Rate_Recommender agent
final_proposal_message = None
for msg in reversed(chat_history):
   if msg.get("position") == "assistant" and msg.get("identify") == rate_recommender_agent.identify:
        if "Customized Introduction:" in msg.get("content material", ""):
           final_proposal_message = msg
           break
if final_proposal_message:
   final_proposal_string = final_proposal_message.get("content material", "Proposal content material not discovered.")
   attempt:
       show(Markdown(final_proposal_string))
   besides NameError:
       print("n(Displaying uncooked Markdown textual content as wealthy output is unavailable)n")
       print(final_proposal_string)


else:
   print("nCould not robotically extract the ultimate proposal from the chat historical past.")
   print("You might must overview the total chat historical past above.")

Pattern Output

Conclusion

On this article, we constructed a venture proposal agent utilizing Llama 4 and AutoGen. The agent successfully gathered shopper necessities, structured the proposal, and delivered knowledgeable doc with clear pricing and timeline breakdowns. AutoGen dealt with the dialog stream, whereas Llama 4 ensured pure, context-aware responses all through. This collaboration simplified shopper communication, providing a streamlined answer for freelancers and consultants to automate proposal era with minimal guide enter.

Llama 4 enhanced the agent’s efficiency with its improved instruction following, higher context retention, and environment friendly few-shot studying. Its capacity to keep up coherence throughout multi-turn dialogues made the proposal era course of extra clever and responsive. Moreover, the mannequin’s quick inference and low price made it appropriate for real-time functions. Collectively, Llama 4 and AutoGen allow highly effective agent workflows that enhance productiveness and professionalism in client-facing duties.

Continuously Requested Questions

Hello, I am Vipin. I am keen about knowledge science and machine studying. I’ve expertise in analyzing knowledge, constructing fashions, and fixing real-world issues. I purpose to make use of knowledge to create sensible options and continue learning within the fields of Knowledge Science, Machine Studying, and NLP.